ApolloRaines
/

Sharona-B2-7B-Jbliterated

Text Generation

cross-attention

Model card Files Files and versions

Sharona-B2-7B-Jbliterated

25 GB

Ctrl+K

Ctrl+K

1 contributor

History: 36 commits

ApolloRaines's picture

Add DeepswapLLM banner to model card

bdd5dc5 verified 5 days ago

model
Upload model/sharona_model.py with huggingface_hub 20 days ago
.gitattributes

1.52 kB
initial commit 20 days ago
M1.txt

216 Bytes
Add file-based M1/M3 context loading, default context files, and quickstart guide 16 days ago
M3.txt

206 Bytes
Add file-based M1/M3 context loading, default context files, and quickstart guide 16 days ago
QUICKSTART.md

5.9 kB
Add file-based M1/M3 context loading, default context files, and quickstart guide 16 days ago
README.md

13.4 kB
Add DeepswapLLM banner to model card 5 days ago
config.py

5.36 kB
Sharona B2 7B - proof of concept (bf16) 20 days ago
hf_tokenizer_config.json

7.31 kB
Sharona B2 7B - proof of concept (bf16) 20 days ago
inference.py

7.77 kB
Add file-based M1/M3 context loading, default context files, and quickstart guide 16 days ago
model_bf16.pt

16.7 GB
xet

Sharona B2 7B - proof of concept (bf16) 20 days ago
model_q8.pt
Detected Pickle imports (5)
- "collections.OrderedDict",
- "torch._utils._rebuild_tensor_v2",
- "torch.BFloat16Storage",
- "torch.CharStorage",
- "torch.FloatStorage"
What is a pickle import?
8.34 GB
xet

Upload model_q8.pt with huggingface_hub 20 days ago
sharona_model.py

24.1 kB
Strip internal architecture details from public files 20 days ago
tokenizer.json

7.03 MB
Sharona B2 7B - proof of concept (bf16) 20 days ago
tokenizer_config.py

2.43 kB
Sharona B2 7B - proof of concept (bf16) 20 days ago